ToxMPNN: A deep learning model for small molecule toxicity prediction.

Machine learning (ML) has shown a great promise in predicting toxicity of small molecules. However, the availability of data for such predictions is often limited. Because of the unsatisfactory performance of models trained on a single toxicity endpoint, we collected toxic small molecules with multiple toxicity endpoints from previous study. The dataset comprises 27 toxic endpoints categorized into seven toxicity classes, namely, carcinogenicity and mutagenicity, acute oral toxicity, respiratory toxicity, irritation and corrosion, cardiotoxicity, CYP450, and endocrine disruption. In addition, a binary classification Common-Toxicity task was added based on the aforementioned dataset. To improve the performance of the models, we added marketed drugs as negative samples. This study presents a toxicity predictive model, ToxMPNN, based on the message passing neural network (MPNN) architecture, aiming to predict the toxicity of small molecules. The results demonstrate that ToxMPNN outperforms other models in capturing toxic features within the molecular structure, resulting in more precise predictions with the ROC_AUC testing score of 0.886 for the Toxicity_drug dataset. Furthermore, it was observed that adding marketed drugs as negative samples not only improves the predictive performance of the binary classification Common-Toxicity task but also enhances the stability of the model prediction. It shows that the graph-based deep learning (DL) algorithms in this study can be used as a trustworthy and effective tool to assess small molecule toxicity in the development of new drugs.

USP7 represses lineage differentiation genes in mouse embryonic stem cells by both catalytic and noncatalytic activities.

USP7, a ubiquitin-specific peptidase (USP), plays an important role in many cellular processes through its catalytic deubiquitination of various substrates. However, its nuclear function that shapes the transcriptional network in mouse embryonic stem cells (mESCs) remains poorly understood. We report that USP7 maintains mESC identity through both catalytic activity-dependent and -independent repression of lineage differentiation genes. Usp7 depletion attenuates SOX2 levels and derepresses lineage differentiation genes thereby compromising mESC pluripotency. Mechanistically, USP7 deubiquitinates and stabilizes SOX2 to repress mesoendodermal (ME) lineage genes. Moreover, USP7 assembles into RYBP-variant Polycomb repressive complex 1 and contributes to Polycomb chromatin-mediated repression of ME lineage genes in a catalytic activity-dependent manner. USP7 deficiency in its deubiquitination function is able to maintain RYBP binding to chromatin for repressing primitive endoderm-associated genes. Our study demonstrates that USP7 harbors both catalytic and noncatalytic activities to repress different lineage differentiation genes, thereby revealing a previously unrecognized role in controlling gene expression for maintaining mESC identity.